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. 60584
    Prev
    Next
    INDEX
    Explanations

    mean reversion

    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
     lune
    -0.09
     máscara
    -0.09
     EF
    -0.08
     छन
    -0.08
     Up
    -0.08
    wic
    -0.08
    ěz
    -0.08
    ëve
    -0.08
     Transparent
    -0.08
     greasy
    -0.07
    POSITIVE LOGITS
     ফিরে
    0.09
    Regression
    0.09
    กลับ
    0.08
     resetting
    0.08
    Deviation
    0.08
     corrective
    0.08
     zurück
    0.08
     regresar
    0.08
     regres
    0.08
    趋
    0.08
    Activations Density 0.003%

    No Known Activations