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. 43691
    Prev
    Next
    INDEX
    Explanations

    Outside areas

    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
     The
    -0.08
     after
    -0.07
     `
    -0.07
    _dims
    -0.07
     (
    -0.07
     Narrow
    -0.07
     S
    -0.07
     restitution
    -0.07
    .Res
    -0.07
     dí
    -0.07
    POSITIVE LOGITS
     outskirts
    0.14
     außerhalb
    0.12
     خارج
    0.12
     suburbs
    0.11
     countryside
    0.11
    'extérieur
    0.10
     commuter
    0.10
     suburban
    0.10
    �
    0.10
    outside
    0.10
    Activations Density 0.112%

    No Known Activations