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. 101391
    Prev
    Next
    INDEX
    Explanations

    high

    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
    cks
    -0.08
    Can't
    -0.08
    問い合わせ
    -0.08
    .Namespace
    -0.08
    (To
    -0.07
     Somehow
    -0.07
    ninger
    -0.07
    してください
    -0.07
     Rpc
    -0.07
     psychopath
    -0.07
    POSITIVE LOGITS
     reputable
    0.09
     surge
    0.09
     тщательно
    0.09
    ™
    0.09
    ®
    0.09
     нашу
    0.09
     onze
    0.08
    0.08
     renom
    0.08
    经过
    0.08
    Activations Density 0.048%

    No Known Activations