© 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. 96715
    Prev
    Next
    INDEX
    Explanations

    form

    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
     gumagamit
    -0.09
     pagitan
    -0.08
     paggamit
    -0.08
     tsakanin
    -0.08
    five
    -0.08
     mellom
    -0.08
    liwo
    -0.08
     verwij
    -0.08
     Between
    -0.08
     giữa
    -0.08
    POSITIVE LOGITS
     vertices
    0.15
     corners
    0.14
     boundaries
    0.14
     part
    0.13
    vertices
    0.13
     together
    0.13
     sides
    0.13
    .vertices
    0.12
     edges
    0.12
    Vertices
    0.12
    Activations Density 0.040%

    No Known Activations