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. 77143
    Prev
    Next
    INDEX
    Explanations

    :

    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
    蕩
    -0.08
     connu
    -0.08
     모습을
    -0.08
    itated
    -0.08
     모습
    -0.08
    vd
    -0.07
     dép
    -0.07
     Бай
    -0.07
     considér
    -0.07
     تیم
    -0.07
    POSITIVE LOGITS
     handlebars
    0.09
    柄
    0.08
     wai
    0.07
    Audio
    0.07
    "If
    0.07
     phr
    0.07
    mus
    0.07
    $output
    0.07
    յանը
    0.07
     relocation
    0.07
    Activations Density 0.004%

    No Known Activations