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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 1782
    Prev
    Next
    INDEX
    Explanations

    1

    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
     maison
    -0.08
    ouvrage
    -0.08
    _PRIORITY
    -0.07
    stry
    -0.07
     gag
    -0.07
     knj
    -0.07
    ുക്ക്
    -0.07
    008
    -0.07
     homepage
    -0.07
     Vigil
    -0.07
    POSITIVE LOGITS
     feiern
    0.08
    ilho
    0.08
    았습니다
    0.07
    았
    0.07
    ()=>
    0.07
     �
    0.07
    .auto
    0.07
    <ul
    0.07
     activos
    0.07
    her
    0.07
    Activations Density 0.000%

    No Known Activations