© 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. 96803
    Prev
    Next
    INDEX
    Explanations

    say "number 4"

    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
    ১৬
    -0.09
     sixteen
    -0.09
     oito
    -0.09
    16
    -0.09
     fourteen
    -0.08
     eight
    -0.08
     ocho
    -0.08
    ８
    -0.08
     øvr
    -0.08
    emeen
    -0.08
    POSITIVE LOGITS
    Up
    0.08
    Perfect
    0.08
    ών
    0.07
    jata
    0.07
    Tak
    0.07
    .Up
    0.07
    $$
    0.07
     conductive
    0.07
    Gaming
    0.07
     Up
    0.07
    Activations Density 0.010%

    No Known Activations