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. 76271
    Prev
    Next
    INDEX
    Explanations

    rd

    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
    сыр
    -0.08
    .Immutable
    -0.08
     Shopify
    -0.08
    UMA
    -0.08
     Sonata
    -0.08
     SOAP
    -0.08
     मह
    -0.08
     trup
    -0.07
    Сред
    -0.07
     SAP
    -0.07
    POSITIVE LOGITS
    策
    0.09
     Raymond
    0.09
     renk
    0.09
    atakan
    0.08
    atherine
    0.08
    _color
    0.07
    hel
    0.07
     Ronald
    0.07
     Lin
    0.07
    Mot
    0.07
    Activations Density 0.002%

    No Known Activations