© 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. 96899
    Prev
    Next
    INDEX
    Explanations

    cv

    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
    买吗
    -0.09
    ুগ
    -0.08
     cadeia
    -0.08
     Opcode
    -0.08
    이버
    -0.07
     stk
    -0.07
     Pec
    -0.07
     dis
    -0.07
     παρα
    -0.07
     month
    -0.07
    POSITIVE LOGITS
    zone
    0.14
    _bridge
    0.12
    Zone
    0.12
    t
    0.11
    Bridge
    0.11
    .Create
    0.10
    Find
    0.10
     zones
    0.10
    _zone
    0.10
    bridge
    0.10
    Activations Density 0.001%

    No Known Activations