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. 23344
    Prev
    Next
    INDEX
    Explanations

    scientific writing

    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
     wheelchair
    -0.08
    nja
    -0.08
     Australian
    -0.08
    Genre
    -0.08
     Voice
    -0.08
    .split
    -0.08
    umbia
    -0.08
     canto
    -0.07
     Rosemary
    -0.07
     genre
    -0.07
    POSITIVE LOGITS
    Notation
    0.10
     notation
    0.09
    -ranging
    0.09
    表示
    0.09
    example
    0.09
     વ્યક્ત
    0.09
     표현
    0.09
     trabal
    0.08
     examples
    0.08
     astronom
    0.08
    Activations Density 0.012%

    No Known Activations