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. 42885
    Prev
    Next
    INDEX
    Explanations

    conditional clauses

    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
     vantagens
    -0.08
     네
    -0.08
    acher
    -0.08
    ame
    -0.08
    advantages
    -0.08
     Firmen
    -0.07
     redes
    -0.07
     Jew
    -0.07
     Rogers
    -0.07
     could
    -0.07
    POSITIVE LOGITS
     resort
    0.11
     resorts
    0.10
     fallback
    0.10
    Fallback
    0.09
    fallback
    0.09
    _FP
    0.08
     impossible
    0.08
    办法
    0.08
     পথ
    0.08
     หา
    0.08
    Activations Density 0.032%

    No Known Activations