© 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. 31576
    Prev
    Next
    INDEX
    Explanations

    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
     contradiction
    -0.08
     வாய
    -0.08
    opt
    -0.08
     aspire
    -0.08
     invert
    -0.08
     તક
    -0.07
     проектов
    -0.07
     விர
    -0.07
    invert
    -0.07
    goto
    -0.07
    POSITIVE LOGITS
     rhythm
    0.11
     rhythmic
    0.11
     ryt
    0.10
     rhythms
    0.10
     ryth
    0.09
     rythme
    0.09
     sintomas
    0.09
     pounding
    0.09
    beats
    0.09
    规律
    0.09
    Activations Density 0.006%

    No Known Activations