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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 129552
    Prev
    Next
    INDEX
    Explanations

    space

    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
     мульт
    -0.08
     aka
    -0.07
     проц
    -0.07
     bull
    -0.07
    .pm
    -0.07
     Su
    -0.07
     pena
    -0.07
    ပ
    -0.07
    lectic
    -0.07
     boasting
    -0.07
    POSITIVE LOGITS
    해서
    0.09
     drauf
    0.08
    OUT
    0.08
    进去
    0.08
     omissions
    0.08
    씩
    0.08
    joni
    0.08
     Ard
    0.08
     asupra
    0.08
    Enterprise
    0.08
    Activations Density 0.004%

    No Known Activations