© 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. 96919
    Prev
    Next
    INDEX
    Explanations

    K

    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
     Überg
    -0.07
     transitions
    -0.07
     asti
    -0.07
     tế
    -0.07
     sicherlich
    -0.07
     biome
    -0.07
     rộng
    -0.07
     zus
    -0.07
     Gramm
    -0.07
     HERE
    -0.07
    POSITIVE LOGITS
    uo
    0.10
    enta
    0.08
    abad
    0.08
    ahala
    0.08
     endorsements
    0.08
    ele
    0.08
    solo
    0.08
    atlas
    0.08
    endu
    0.08
    	Point
    0.08
    Activations Density 0.000%

    No Known Activations