© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129339
    Prev
    Next
    INDEX
    Explanations

    и

    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
     REPORT
    -0.08
     alleviate
    -0.08
     catal
    -0.08
     inaugur
    -0.08
     erupt
    -0.07
     kiire
    -0.07
    મા
    -0.07
     એવો
    -0.07
    国产
    -0.07
    _act
    -0.07
    POSITIVE LOGITS
    لاب
    0.09
     waterfront
    0.08
    _WIFI
    0.08
    ظه
    0.08
     Holt
    0.08
     Imag
    0.08
    Waiting
    0.08
    lege
    0.07
     beachfront
    0.07
     wifi
    0.07
    Activations Density 0.001%

    No Known Activations