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. 120467
    Prev
    Next
    INDEX
    Explanations

    code examples

    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
     отключ
    -0.07
     disrupting
    -0.07
     обязатель
    -0.07
     disturb
    -0.07
    orem
    -0.07
    Adornment
    -0.07
     divert
    -0.07
    ОМ
    -0.07
    ाळ
    -0.07
    _PRESENT
    -0.07
    POSITIVE LOGITS
     underlying
    0.11
     underneath
    0.10
    Underlying
    0.10
    feo
    0.09
    whatever
    0.09
     whatever
    0.09
     seben
    0.08
    .Util
    0.08
     Under
    0.08
     whichever
    0.08
    Activations Density 0.030%

    No Known Activations