© 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. 99897
    Prev
    Next
    INDEX
    Explanations

    difference, negation

    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
    те
    -0.08
     મહ
    -0.08
    _cli
    -0.08
    몰
    -0.08
     বিল
    -0.08
    611
    -0.07
    くだ
    -0.07
     ense
    -0.07
     Casablanca
    -0.07
     enqu
    -0.07
    POSITIVE LOGITS
    Adjacent
    0.10
     adjacent
    0.09
    adina
    0.09
    Contrast
    0.08
    neighbor
    0.08
     Contrast
    0.08
     taboo
    0.08
    ellent
    0.08
     night's
    0.08
     Forbidden
    0.08
    Activations Density 0.017%

    No Known Activations