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. 41978
    Prev
    Next
    INDEX
    Explanations

    book excerpts

    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
    -defined
    -0.08
    viel
    -0.08
     mabilis
    -0.08
    $m
    -0.08
    _DMA
    -0.08
     Hau
    -0.08
     Funcion
    -0.08
    Funcion
    -0.08
     অনুভ
    -0.07
     IPTV
    -0.07
    POSITIVE LOGITS
     armies
    0.09
     ег
    0.08
     army
    0.08
    军
    0.08
    ukset
    0.08
     siege
    0.08
    ுக
    0.08
     bantuan
    0.07
    剧情
    0.07
     timpul
    0.07
    Activations Density 0.009%

    No Known Activations