© 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. 102971
    Prev
    Next
    INDEX
    Explanations

    normally

    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
    izing
    -0.09
     groundwork
    -0.08
    -ish
    -0.08
    -м
    -0.08
     ofta
    -0.07
    (I
    -0.07
     Vaak
    -0.07
    Define
    -0.07
    -п
    -0.07
    ").
    -0.07
    POSITIVE LOGITS
     would
    0.14
    would
    0.14
    'aurais
    0.12
     WOULD
    0.11
     would've
    0.11
     આવા
    0.11
     auraient
    0.11
     wouldnt
    0.11
     potentially
    0.10
     Would
    0.10
    Activations Density 0.014%

    No Known Activations