© 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. 25001
    Prev
    Next
    INDEX
    Explanations

    classifier

    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
    যোগ
    -0.08
    цар
    -0.08
    aceut
    -0.07
     tested
    -0.07
    subject
    -0.07
    योग
    -0.07
     recur
    -0.07
     acquisition
    -0.07
     definitions
    -0.07
     subject
    -0.07
    POSITIVE LOGITS
     riffs
    0.09
     riff
    0.09
     apesar
    0.09
     Gay
    0.08
     가
    0.08
     bezpe
    0.08
     bezpieczeń
    0.08
     trots
    0.08
     GRO
    0.08
    ustre
    0.08
    Activations Density 0.000%

    No Known Activations