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. 54211
    Prev
    Next
    INDEX
    Explanations

    assistant

    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
    త్న
    -0.07
     Type
    -0.07
     Saison
    -0.07
    ట్టి
    -0.07
    øst
    -0.07
     السياسة
    -0.07
     prostit
    -0.07
    _builder
    -0.07
    rats
    -0.07
    _dom
    -0.07
    POSITIVE LOGITS
    .foreach
    0.10
     unreachable
    0.08
     behalf
    0.08
     συνεχ
    0.08
    !==
    0.08
     CCP
    0.07
    UTILITY
    0.07
     ανο
    0.07
    .material
    0.07
     PTO
    0.07
    Activations Density 0.018%

    No Known Activations