© 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. 48491
    Prev
    Next
    INDEX
    Explanations

    geometry and equations

    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
    (bb
    -0.18
    (rr
    -0.18
    PPP
    -0.18
     cbd
    -0.18
     bst
    -0.17
    bbb
    -0.17
     gta
    -0.17
    bbc
    -0.17
    (cc
    -0.17
    (bp
    -0.17
    POSITIVE LOGITS
     KOYO
    0.12
     |
    0.10
     ||
    0.10
    ـ
    0.10
     \(
    0.10
     Ӯ
    0.09
    <|constrain|>
    0.09
     =
    0.09
    	RTLR
    0.09
     length
    0.09
    Activations Density 0.268%

    No Known Activations