Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 106107
    Prev
    Next
    INDEX
    Explanations

    の

    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
    461
    -0.08
    588
    -0.08
    (
    -0.07
    (fp
    -0.07
     Published
    -0.07
    451
    -0.07
     conclusions
    -0.07
     Dor
    -0.07
    angana
    -0.07
    hat
    -0.07
    POSITIVE LOGITS
    ivan
    0.09
    Ace
    0.08
    ivirus
    0.08
     sekitar
    0.08
    ક્સ
    0.08
    -fluid
    0.08
    yang
    0.08
    Justice
    0.08
     tans
    0.08
    ivore
    0.07
    Activations Density 0.002%

    No Known Activations