© 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. 51042
    Prev
    Next
    INDEX
    Explanations

    Str

    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
    06
    -0.08
    toni
    -0.08
     punten
    -0.08
    加勒比
    -0.08
     BEN
    -0.08
     tapas
    -0.08
    女人
    -0.07
     TOK
    -0.07
     OCC
    -0.07
     gani
    -0.07
    POSITIVE LOGITS
     Wireless
    0.08
    �
    0.08
     му
    0.08
    .Desc
    0.08
    .messaging
    0.07
     agreed
    0.07
    .Task
    0.07
     harmed
    0.07
    .ref
    0.07
     общ
    0.07
    Activations Density 0.003%

    No Known Activations