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. 44167
    Prev
    Next
    INDEX
    Explanations

    profile

    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
    chool
    -0.08
    ంతో
    -0.08
     ਨਾਲ
    -0.08
     adventure
    -0.08
    chakra
    -0.08
     తో
    -0.08
     prakt
    -0.08
     tekn
    -0.08
     aventuras
    -0.08
     துண
    -0.08
    POSITIVE LOGITS
     registrar
    0.09
    Mappings
    0.08
    registr
    0.08
    IDs
    0.08
     Mapping
    0.08
    -pencil
    0.08
     mappings
    0.07
    Registr
    0.07
     Registrierung
    0.07
    .Cl
    0.07
    Activations Density 0.010%

    No Known Activations