© 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. 19-RESID-POST-AA
    11. 102644
    Prev
    Next
    INDEX
    Explanations

    100

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =request
    -0.08
     Бога
    -0.08
     Ск
    -0.08
     Госп
    -0.08
    =True
    -0.08
     已
    -0.07
    _separator
    -0.07
     Cad
    -0.07
     Але
    -0.07
    .Cascade
    -0.07
    POSITIVE LOGITS
     unités
    0.13
    units
    0.12
     units
    0.12
     convenient
    0.12
     unidades
    0.11
     jednost
    0.11
     jednot
    0.11
    Units
    0.11
     unit
    0.11
     യൂണ
    0.11
    Activations Density 0.008%

    No Known Activations