© 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. 48577
    Prev
    Next
    INDEX
    Explanations

    at

    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
     Above
    -0.10
    umbnails
    -0.09
     aprim
    -0.09
    .Drawing
    -0.08
     וכו
    -0.08
     gewone
    -0.08
    -Amer
    -0.08
     titles
    -0.08
     отлично
    -0.08
     깨
    -0.08
    POSITIVE LOGITS
     endpoint
    0.23
    endpoint
    0.20
    (endpoint
    0.20
    _endpoint
    0.19
    Endpoint
    0.19
    .endpoint
    0.18
     boundary
    0.18
     Endpoint
    0.18
     endpoints
    0.17
    _ENDPOINT
    0.17
    Activations Density 0.039%

    No Known Activations