© 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. 94704
    Prev
    Next
    INDEX
    Explanations

    Expand

    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
    .power
    -0.08
    нең
    -0.08
     ਦੁ
    -0.08
    .BASELINE
    -0.08
    oked
    -0.07
     defended
    -0.07
     regained
    -0.07
     waliin
    -0.07
    -0.07
     amplified
    -0.07
    POSITIVE LOGITS
    adat
    0.08
    ublish
    0.08
    Targets
    0.07
     സ്ക
    0.07
     tightening
    0.07
    :The
    0.07
    /sub
    0.07
     settings
    0.07
     strand
    0.07
    arar
    0.07
    Activations Density 0.000%
    No Known Activations