© 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 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. 113269
    Prev
    Next
    INDEX
    Explanations

    on

    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
     നിയന്ത്ര
    -0.09
     Regul
    -0.08
     വൈ
    -0.08
     Independ
    -0.08
    ക്രമ
    -0.07
     ട
    -0.07
     ദേശീയ
    -0.07
     ನಿಯ
    -0.07
     ക്ര
    -0.07
     kanthi
    -0.07
    POSITIVE LOGITS
    already
    0.08
     tẹlẹ
    0.08
    િયા
    0.08
     already
    0.08
     redan
    0.08
     zaten
    0.08
     bereits
    0.08
     demais
    0.08
     بالفعل
    0.08
    ्वी
    0.07
    Activations Density 0.047%

    No Known Activations