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. 1860
    Prev
    Next
    INDEX
    Explanations

    world's

    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
    ovo
    -0.08
    wish
    -0.08
     aí
    -0.08
     Masters
    -0.07
     PARTIC
    -0.07
    .INSTANCE
    -0.07
     occult
    -0.07
    בוד
    -0.07
    _OV
    -0.07
    ég
    -0.07
    POSITIVE LOGITS
    �
    0.08
     он
    0.08
    �
    0.08
     Lionel
    0.08
     Copper
    0.08
     könne
    0.07
     واض
    0.07
    gli
    0.07
    470
    0.07
     devastating
    0.07
    Activations Density 0.002%

    No Known Activations