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. 59047
    Prev
    Next
    INDEX
    Explanations

    Mathematical mappings and functions

    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
     flotation
    -0.08
    ドル
    -0.08
     airborne
    -0.08
     buoy
    -0.08
     Brigade
    -0.08
    -plane
    -0.08
    buffer
    -0.08
     plane
    -0.08
     descont
    -0.07
     �
    -0.07
    POSITIVE LOGITS
     ಬಿಜೆ
    0.10
    .Mapping
    0.09
    .mapping
    0.09
     отображ
    0.09
     mappings
    0.09
     mapping
    0.09
    Mappings
    0.09
    Mapping
    0.09
     Mapping
    0.09
     trivial
    0.09
    Activations Density 0.032%

    No Known Activations