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. 55626
    Prev
    Next
    INDEX
    Explanations

    sealed

    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
     Dye
    -0.08
     баж
    -0.08
    Yaw
    -0.08
    _body
    -0.08
    _ctx
    -0.08
     Bratis
    -0.08
    (date
    -0.07
     onboard
    -0.07
    (name
    -0.07
    _lineno
    -0.07
    POSITIVE LOGITS
    éné
    0.08
     متنوعة
    0.08
     residencial
    0.08
     مناف
    0.08
     vaihtoe
    0.08
    ouro
    0.07
     Alternatives
    0.07
    -ta
    0.07
     résident
    0.07
     alternatif
    0.07
    Activations Density 0.002%

    No Known Activations