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. 52908
    Prev
    Next
    INDEX
    Explanations

    plt

    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
    oidal
    -0.08
     बारिश
    -0.08
    psyon
    -0.08
    THE
    -0.08
     SCH
    -0.08
    .some
    -0.08
    ्ब
    -0.08
    âteau
    -0.08
    .has
    -0.08
    pleados
    -0.08
    POSITIVE LOGITS
    incer
    0.07
     dis
    0.07
     goal
    0.07
     disso
    0.07
     vocabulary
    0.07
    incerely
    0.07
     ide
    0.07
     vule
    0.07
     vocab
    0.07
     nela
    0.07
    Activations Density 0.000%

    No Known Activations