© 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. 54862
    Prev
    Next
    INDEX
    Explanations

    表

    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
    anon
    -0.09
    衣
    -0.08
    Iterable
    -0.08
    iram
    -0.08
     vox
    -0.07
    ိုး
    -0.07
     Afterwards
    -0.07
     chac
    -0.07
    linge
    -0.07
     regards
    -0.07
    POSITIVE LOGITS
     прибор
    0.10
     readings
    0.09
    _read
    0.08
     kopp
    0.08
     اتصال
    0.08
     dial
    0.08
     barrels
    0.08
    _reader
    0.08
    /cal
    0.08
    manship
    0.08
    Activations Density 0.006%

    No Known Activations