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. 76463
    Prev
    Next
    INDEX
    Explanations

    attribute

    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
     Groß
    -0.08
    rium
    -0.08
     Esper
    -0.08
    _SENSOR
    -0.07
    -With
    -0.07
     ينب
    -0.07
     émer
    -0.07
     κόσ
    -0.07
     dop
    -0.07
    ्ख
    -0.07
    POSITIVE LOGITS
    γελ
    0.09
    restrict
    0.08
     Fact
    0.07
    gil
    0.07
     blessed
    0.07
     trước
    0.07
     aprend
    0.07
     আগে
    0.07
     hammock
    0.07
    Fact
    0.07
    Activations Density 0.001%

    No Known Activations