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. 119152
    Prev
    Next
    INDEX
    Explanations

    commas and parentheses

    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
    पू
    -0.08
    मैं
    -0.07
    (power
    -0.07
    票
    -0.07
    करी
    -0.07
    По
    -0.07
    ibernate
    -0.07
    .power
    -0.07
     tears
    -0.06
     juxtap
    -0.06
    POSITIVE LOGITS
     née
    0.09
    inese
    0.09
    uslar
    0.08
     Victoria
    0.08
     Cuisine
    0.08
     Mascul
    0.08
     Grâce
    0.07
     Motto
    0.07
     Sexo
    0.07
     Regency
    0.07
    Activations Density 0.000%

    No Known Activations