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. 11-RESID-POST-AA
    6. 30767
    Prev
    Next
    INDEX
    Explanations

    evil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _inc
    -0.08
    andel
    -0.08
     entourage
    -0.08
     taş
    -0.08
     impul
    -0.08
     insulated
    -0.08
     diap
    -0.08
    ungu
    -0.08
     يول
    -0.08
     لباس
    -0.08
    POSITIVE LOGITS
    iented
    0.09
    然
    0.08
    162
    0.08
     fără
    0.07
    ંપ
    0.07
    pless
    0.07
    _REC
    0.07
    posal
    0.07
    ả
    0.07
    ાહ
    0.07
    Activations Density 0.000%

    No Known Activations