© 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. 99268
    Prev
    Next
    INDEX
    Explanations

    mammography

    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
     menu
    -0.08
     règle
    -0.07
     refrain
    -0.07
     akc
    -0.07
     arranger
    -0.07
     arrang
    -0.07
     objects
    -0.07
     section
    -0.07
     Bahnhof
    -0.07
     groundwork
    -0.07
    POSITIVE LOGITS
     psoriasis
    0.09
     خشک
    0.09
    癌
    0.08
     discap
    0.08
    迟
    0.08
     威
    0.08
    osaic
    0.08
    ennial
    0.08
     câncer
    0.08
     CSA
    0.08
    Activations Density 0.002%

    No Known Activations