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. 45200
    Prev
    Next
    INDEX
    Explanations

    black holes

    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
     אם
    -0.08
     tion
    -0.08
    .pitch
    -0.08
     wenn
    -0.08
     shortages
    -0.08
    Если
    -0.08
     fynd
    -0.08
    .SQL
    -0.08
     Wenn
    -0.08
     nida
    -0.08
    POSITIVE LOGITS
    blocking
    0.08
    _candidates
    0.08
     barber
    0.08
    _named
    0.07
    лған
    0.07
    anum
    0.07
    asm
    0.07
     responsáveis
    0.07
    ligt
    0.07
    Candidates
    0.07
    Activations Density 0.001%

    No Known Activations