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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110979
    Prev
    Next
    INDEX
    Explanations

    negative contractions

    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
    hat
    -0.09
    -chart
    -0.08
    (Car
    -0.07
    টির
    -0.07
     beauties
    -0.07
     Green
    -0.07
     verde
    -0.07
     tích
    -0.07
     Horizons
    -0.07
    (post
    -0.07
    POSITIVE LOGITS
     unsure
    0.10
     unable
    0.09
     difficult
    0.09
     Difficult
    0.08
     zároveň
    0.08
     hes
    0.08
     peripheral
    0.08
     gleichzeitig
    0.08
     uncertain
    0.07
     dificuldade
    0.07
    Activations Density 0.067%

    No Known Activations