© 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. 11-RESID-POST-AA
    11. 71324
    Prev
    Next
    INDEX
    Explanations

    form of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    worked
    -0.09
     clogged
    -0.08
    _RULE
    -0.08
     Deals
    -0.08
     completely
    -0.08
    estellt
    -0.08
    rook
    -0.08
    -piece
    -0.08
    rules
    -0.07
     cuentos
    -0.07
    POSITIVE LOGITS
     spirituality
    0.08
    эз
    0.08
     спорта
    0.08
     escritura
    0.08
     Dys
    0.08
     терапии
    0.08
     shir
    0.08
     энергии
    0.07
     Buddhism
    0.07
    'énergie
    0.07
    Activations Density 0.026%

    No Known Activations