© 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. 23-RESID-POST-AA
    11. 48187
    Prev
    Next
    INDEX
    Explanations

    enc

    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
     罗
    -0.08
    ihan
    -0.08
    (ro
    -0.08
     catt
    -0.08
    ro
    -0.08
    роф
    -0.08
     esc
    -0.08
     lorg
    -0.07
     捕
    -0.07
     રજૂ
    -0.07
    POSITIVE LOGITS
    aqu
    0.08
     بالق
    0.08
    emm
    0.07
    ors
    0.07
    eneuve
    0.07
    �
    0.07
    ਪੀ
    0.07
    ene
    0.07
    зем
    0.07
    پی
    0.07
    Activations Density 0.000%

    No Known Activations