© 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. 23-RESID-POST-AA
    11. 50616
    Prev
    Next
    INDEX
    Explanations

    aspects

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ezie
    -0.09
    authorize
    -0.08
    assoc
    -0.07
     mch
    -0.07
    اعم
    -0.07
     atribut
    -0.07
    ً
    -0.07
    action
    -0.07
    attribute
    -0.07
    ремен
    -0.07
    POSITIVE LOGITS
    paragus
    0.13
    uming
    0.13
    ual
    0.13
    UAL
    0.12
    PECT
    0.12
    pects
    0.11
    ptomatic
    0.11
    ymmetric
    0.11
    Zeneca
    0.11
    amblea
    0.11
    Activations Density 0.085%

    No Known Activations