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. 112625
    Prev
    Next
    INDEX
    Explanations

    value

    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
     Konk
    -0.07
     Atlet
    -0.07
     Beau
    -0.07
    停
    -0.07
     Agenda
    -0.07
     Infos
    -0.07
    _validate
    -0.07
     kras
    -0.07
     validated
    -0.07
     whistles
    -0.07
    POSITIVE LOGITS
    farm
    0.10
     húmed
    0.09
    DOWN
    0.09
    ferm
    0.08
     حر
    0.08
     tonal
    0.08
    Farm
    0.08
    far
    0.08
     humide
    0.08
     aproxima
    0.08
    Activations Density 0.002%

    No Known Activations