© 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. 7-RESID-POST-AA
    11. 1396
    Prev
    Next
    INDEX
    Explanations

    technical/mathematical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oil
    -0.08
     sidan
    -0.08
     sal
    -0.08
     etm
    -0.07
    295
    -0.07
    eyey
    -0.07
     hele
    -0.07
     tans
    -0.07
    _TS
    -0.07
     hoja
    -0.07
    POSITIVE LOGITS
     apparent
    0.08
    prest
    0.07
    Stars
    0.07
     �
    0.07
     Miranda
    0.07
    Examples
    0.07
    看来
    0.07
    Patterns
    0.07
     �
    0.07
    patterns
    0.07
    Activations Density 2.112%

    No Known Activations