Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 12687
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     परिच
    -0.08
    lí
    -0.08
    ्यास
    -0.08
    ात्मक
    -0.07
    ละ
    -0.07
    套路
    -0.07
     enforcement
    -0.07
    tbody
    -0.07
    ゴ
    -0.07
     Northwest
    -0.07
    POSITIVE LOGITS
    Arqu
    0.08
     exp
    0.08
    ÜR
    0.08
     SOUR
    0.08
    [cur
    0.08
     Kant
    0.08
    gerufen
    0.07
     ARCH
    0.07
     Urb
    0.07
     suis
    0.07
    Activations Density 0.004%

    No Known Activations