© 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. 65395
    Prev
    Next
    INDEX
    Explanations

    etc

    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
    _AB
    -0.08
    =NULL
    -0.08
     diri
    -0.07
    _ASSUME
    -0.07
    祝
    -0.07
    天
    -0.07
     Albert
    -0.07
     �
    -0.07
    ల్
    -0.07
    _Find
    -0.07
    POSITIVE LOGITS
     highway
    0.08
     anderes
    0.08
    ilver
    0.08
     village
    0.08
     specification
    0.08
     miscell
    0.08
    что
    0.07
    γμα
    0.07
    קייט
    0.07
     dozen
    0.07
    Activations Density 0.004%

    No Known Activations