© 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. 7710
    Prev
    Next
    INDEX
    Explanations

    card pairs

    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
    liv
    -0.08
     Moyen
    -0.08
     lifestyles
    -0.08
     impotence
    -0.07
     prenant
    -0.07
    ROPERTY
    -0.07
     Fox
    -0.07
     dikkat
    -0.07
     Lamin
    -0.07
     Pard
    -0.07
    POSITIVE LOGITS
     sleepers
    0.09
    Duplicates
    0.08
     matéri
    0.08
     duplicate
    0.08
    astic
    0.08
    Abb
    0.08
     الكن
    0.08
     темат
    0.08
     silk
    0.08
     ethnic
    0.08
    Activations Density 0.009%

    No Known Activations