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. 102949
    Prev
    Next
    INDEX
    Explanations

    Accessibility/WAVE testing

    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
     Pode
    -0.09
     Prins
    -0.08
     Pill
    -0.08
     angenehm
    -0.08
     ekspl
    -0.08
     poter
    -0.08
     Klub
    -0.08
     pill
    -0.08
     potens
    -0.08
     vyd
    -0.08
    POSITIVE LOGITS
    申
    0.09
     autism
    0.09
    र्शन
    0.08
    .override
    0.08
     postings
    0.08
     retrieved
    0.08
    .Assign
    0.07
     metropolitan
    0.07
    .yahoo
    0.07
     Yorkshire
    0.07
    Activations Density 0.002%

    No Known Activations