© 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. 94593
    Prev
    Next
    INDEX
    Explanations

    line

    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
     Lager
    -0.09
     lager
    -0.09
     Ogun
    -0.08
     Iterable
    -0.08
    aye
    -0.08
     Gamb
    -0.08
    üg
    -0.07
    ailable
    -0.07
    imente
    -0.07
    मान
    -0.07
    POSITIVE LOGITS
     가운데
    0.10
     centrally
    0.09
     splitting
    0.09
     ridge
    0.09
    entral
    0.08
     глад
    0.08
     forehead
    0.08
     중앙
    0.08
     раздел
    0.08
     przeb
    0.08
    Activations Density 0.014%

    No Known Activations