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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 53175
    Prev
    Next
    INDEX
    Explanations

    .pack

    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
     अर्थात
    -0.08
     typings
    -0.08
    לפ
    -0.08
    谋
    -0.08
     zabo
    -0.08
     Clarkson
    -0.08
    meh
    -0.08
    .shiro
    -0.08
     cucina
    -0.08
     womb
    -0.08
    POSITIVE LOGITS
    -end
    0.08
     בצורה
    0.07
    (fill
    0.07
    _descr
    0.07
    -h
    0.07
     देना
    0.07
     details
    0.07
    grav
    0.07
    Expose
    0.07
    ursed
    0.07
    Activations Density 0.001%

    No Known Activations