© 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. 11-RESID-POST-AA
    11. 29638
    Prev
    Next
    INDEX
    Explanations

    Non-English, document structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     एक्स
    -0.07
     аксесс
    -0.07
    ierer
    -0.07
    rette
    -0.07
    _od
    -0.07
     alabara
    -0.07
    ('[
    -0.07
    ahid
    -0.07
    _L
    -0.07
     dersom
    -0.07
    POSITIVE LOGITS
     whilst
    0.09
     الى
    0.09
     Basically
    0.09
    �
    0.09
    細
    0.08
     kinda
    0.08
     marvelous
    0.08
     hilarious
    0.08
    Basically
    0.08
    Whilst
    0.08
    Activations Density 0.144%

    No Known Activations