© 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. 5976
    Prev
    Next
    INDEX
    Explanations

    say aa

    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
    Ğ
    -0.09
    .General
    -0.08
    иниң
    -0.08
    Participant
    -0.08
    IÓN
    -0.08
    RQ
    -0.08
    .Is
    -0.08
    Integer
    -0.08
    _GT
    -0.07
    үнки
    -0.07
    POSITIVE LOGITS
    aa
    0.25
     aa
    0.19
    aaa
    0.17
    haa
    0.16
    -aa
    0.16
    aas
    0.16
    aaaa
    0.15
    аа
    0.15
     aas
    0.14
    raa
    0.14
    Activations Density 0.002%

    No Known Activations