Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 112889
    Prev
    Next
    INDEX
    Explanations

    logging

    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
     menc
    -0.08
     kurang
    -0.08
     computers
    -0.08
    584
    -0.08
     loosely
    -0.07
     maison
    -0.07
    lha
    -0.07
     casa
    -0.07
     voila
    -0.07
    оза
    -0.07
    POSITIVE LOGITS
    arrival
    0.08
    fn
    0.08
    -scale
    0.07
     आगामी
    0.07
    (theta
    0.07
    ipid
    0.07
    /status
    0.07
    _msg
    0.07
    :k
    0.07
     Betrag
    0.07
    Activations Density 0.002%

    No Known Activations