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. 49525
    Prev
    Next
    INDEX
    Explanations

    GUI programming

    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
     tabletop
    -0.08
    bern
    -0.07
    ("""
    -0.07
    _DE
    -0.07
     Denmark
    -0.07
    ptable
    -0.07
     favors
    -0.07
     REF
    -0.07
     Atlanta
    -0.07
    /table
    -0.07
    POSITIVE LOGITS
    aksanaan
    0.09
     akad
    0.08
     nok
    0.08
    ാ�
    0.08
    理念
    0.08
     ergibt
    0.08
     elas
    0.08
    ène
    0.07
    anke
    0.07
    指导
    0.07
    Activations Density 0.000%

    No Known Activations