© 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. 23-RESID-POST-AA
    11. 97419
    Prev
    Next
    INDEX
    Explanations

    say or

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (or
    -0.14
    /or
    -0.13
    /oder
    -0.12
     zumindest
    -0.10
    or
    -0.10
    —or
    -0.09
    (and
    -0.09
    そして
    -0.09
    orados
    -0.08
    /ou
    -0.08
    POSITIVE LOGITS
     אדער
    0.16
     અથ
    0.15
     ಅಥ
    0.15
     אָדער
    0.14
     ან
    0.14
     �
    0.12
    ห
    0.12
    还是假的
    0.11
     kumbe
    0.11
     કે
    0.11
    Activations Density 0.512%

    No Known Activations