© 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. 31055
    Prev
    Next
    INDEX
    Explanations

    ifying

    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
    (V
    -0.08
     swinging
    -0.08
    Slip
    -0.07
     Association
    -0.07
    Association
    -0.07
     swung
    -0.07
    .Absolute
    -0.07
     Recycling
    -0.07
    che
    -0.07
     Island
    -0.07
    POSITIVE LOGITS
     уточ
    0.11
     clarification
    0.10
     aclar
    0.10
     �
    0.10
     esclarecer
    0.10
     Clar
    0.10
    询
    0.10
    明确
    0.09
     clar
    0.09
     onzeker
    0.09
    Activations Density 0.029%

    No Known Activations