© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18933
    Prev
    Next
    INDEX
    Explanations

    Large sums of money

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     einfachen
    -0.09
     beginners
    -0.09
     simplest
    -0.08
     bahwa
    -0.08
     хорош
    -0.08
     همان
    -0.08
     duplex
    -0.08
     principi
    -0.08
    เดียว
    -0.08
     goede
    -0.08
    POSITIVE LOGITS
     billions
    0.18
     bilhões
    0.16
     millions
    0.16
     Milliarden
    0.15
     milliards
    0.15
     કરોડ
    0.15
     milhões
    0.15
     billion
    0.15
     totaling
    0.15
     amassed
    0.15
    Activations Density 0.155%

    No Known Activations