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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 31473
    Prev
    Next
    INDEX
    Explanations

    math inequalities

    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
    �
    -0.08
     Sour
    -0.08
    麦
    -0.08
     bred
    -0.08
     réalisé
    -0.08
     passer
    -0.08
     deviennent
    -0.08
    platte
    -0.08
     маг
    -0.07
     nessa
    -0.07
    POSITIVE LOGITS
    en
    0.08
    akeup
    0.08
     fiel
    0.07
    azu
    0.07
    ilen
    0.07
    statement
    0.07
     že
    0.07
    CSI
    0.07
     Bela
    0.07
    mless
    0.07
    Activations Density 0.022%

    No Known Activations