© 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. 48023
    Prev
    Next
    INDEX
    Explanations

    Unicode replacement character

    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
    ાય
    -0.10
    ಿಯ
    -0.10
    -0.10
    ି
    -0.09
    ಯ
    -0.09
    ಿಪ
    -0.09
    ilik
    -0.08
    ಾಶ
    -0.08
    ites
    -0.08
    య
    -0.08
    POSITIVE LOGITS
    �
    0.24
    �이
    0.17
    れ
    0.13
    �
    0.11
    ნილ
    0.11
    რად
    0.11
    ნით
    0.10
    һының
    0.10
    რება
    0.10
    �니다
    0.10
    Activations Density 0.025%
    No Known Activations