© 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. 78436
    Prev
    Next
    INDEX
    Explanations

    A

    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
     dynasty
    -0.08
     pave
    -0.07
     memas
    -0.07
    ERING
    -0.07
     synchronous
    -0.07
     circ
    -0.07
    /latest
    -0.07
     paving
    -0.07
     triang
    -0.07
     domest
    -0.07
    POSITIVE LOGITS
    permission
    0.09
    taí
    0.08
    brev
    0.08
    қан
    0.08
    brevi
    0.08
    apụ
    0.08
    ора
    0.07
    ือ
    0.07
    это
    0.07
    thank
    0.07
    Activations Density 0.001%

    No Known Activations