© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 91212
    Prev
    Next
    INDEX
    Explanations

    Forgetting

    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
    ivari
    -0.08
    Matched
    -0.08
     matched
    -0.08
    рап
    -0.07
     seismic
    -0.07
     ribbons
    -0.07
     revenues
    -0.07
    _rat
    -0.07
     diode
    -0.07
    igend
    -0.07
    POSITIVE LOGITS
     기억
    0.11
     dementia
    0.10
     geheugen
    0.09
     inability
    0.09
     bewilder
    0.09
     Alzheimer's
    0.09
     oubl
    0.09
     impair
    0.09
     impaired
    0.09
     Fog
    0.09
    Activations Density 0.016%

    No Known Activations