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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 16337
    Prev
    Next
    INDEX
    Explanations

    coding instructions

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     biotechnology
    -0.08
     biotech
    -0.08
     vero
    -0.08
     JMP
    -0.08
     bunk
    -0.08
    iedo
    -0.07
    .NORMAL
    -0.07
     HP
    -0.07
     ausge
    -0.07
     Directors
    -0.07
    POSITIVE LOGITS
    _↵
    0.10
    Rather
    0.09
     নামে
    0.09
     Rather
    0.09
    _↵↵
    0.09
     invés
    0.09
    Similarly
    0.09
    Estimate
    0.08
     সংগ্র
    0.08
    Epoch
    0.08
    Activations Density 0.006%

    No Known Activations