© 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. 51427
    Prev
    Next
    INDEX
    Explanations

    мас

    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
    ancis
    -0.08
    estan
    -0.08
    uth
    -0.08
    .boot
    -0.08
    ’e
    -0.07
    uc
    -0.07
    utsche
    -0.07
     eche
    -0.07
     Boot
    -0.07
    ecu
    -0.07
    POSITIVE LOGITS
    cara
    0.12
    キング
    0.12
    Más
    0.11
    caras
    0.11
     mascara
    0.10
     máscara
    0.10
    кир
    0.10
    кара
    0.10
    ки
    0.10
     Más
    0.10
    Activations Density 0.001%

    No Known Activations