© 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. 18502
    Prev
    Next
    INDEX
    Explanations

    say numbers

    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
    1
    -0.10
    ১
    -0.09
     jedan
    -0.09
     or
    -0.09
    /basic
    -0.08
     /
    -0.08
     или
    -0.08
     pertama
    -0.08
     Firstly
    -0.08
    .One
    -0.08
    POSITIVE LOGITS
    ៦
    0.12
    ៧
    0.12
     sixth
    0.11
     الساد
    0.11
     հաջ
    0.11
     sexto
    0.10
     eighth
    0.10
     вось
    0.10
    ៥
    0.10
    ６
    0.10
    Activations Density 0.017%

    No Known Activations