© 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. 25219
    Prev
    Next
    INDEX
    Explanations

    negative

    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
     Irene
    -0.07
     pest
    -0.07
    }},
    -0.07
    രം
    -0.07
     Gao
    -0.07
    .radio
    -0.07
     discovery
    -0.07
     Discovery
    -0.07
    _resolution
    -0.07
    κου
    -0.07
    POSITIVE LOGITS
     بيان
    0.09
     oppos
    0.09
     reversing
    0.09
     opposite
    0.09
     reversal
    0.09
     يك
    0.08
    uun
    0.08
    SCRIBE
    0.08
     revers
    0.07
     opposing
    0.07
    Activations Density 0.020%

    No Known Activations