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. 78729
    Prev
    Next
    INDEX
    Explanations

    module

    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
    _ENTRY
    -0.07
    THING
    -0.07
     conventional
    -0.07
    additional
    -0.07
    NE
    -0.07
    normalize
    -0.07
     NE
    -0.07
    PSD
    -0.07
    078
    -0.07
    _dtype
    -0.07
    POSITIVE LOGITS
    .exports
    0.10
    (exports
    0.09
    cab
    0.08
     exports
    0.08
     atribut
    0.08
    Cab
    0.08
     rang
    0.08
    iktok
    0.08
     mod
    0.08
    mod
    0.08
    Activations Density 0.001%

    No Known Activations