© 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. 47974
    Prev
    Next
    INDEX
    Explanations

    matching strings

    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
     items
    -0.08
    Descriptions
    -0.08
     descriptions
    -0.08
    items
    -0.08
    Items
    -0.08
    Sized
    -0.08
    priced
    -0.08
    Описание
    -0.08
    scores
    -0.07
     Describe
    -0.07
    POSITIVE LOGITS
    /name
    0.14
    /id
    0.13
    _MATCH
    0.13
    匹
    0.13
     string
    0.13
    _prefix
    0.13
     suffix
    0.13
     совп
    0.12
    _suffix
    0.12
     matching
    0.12
    Activations Density 0.080%

    No Known Activations