Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 77418
    Prev
    Next
    INDEX
    Explanations

    pre-order

    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
    tick
    -0.09
    成年人
    -0.08
    abino
    -0.08
    Tick
    -0.07
     struct
    -0.07
    ticks
    -0.07
    /List
    -0.07
     confirms
    -0.07
     uzun
    -0.07
     titres
    -0.07
    POSITIVE LOGITS
     eager
    0.09
     eagerly
    0.08
    -first
    0.08
     prioridad
    0.08
     liter
    0.08
     subsection
    0.07
     greedy
    0.07
     αξιο
    0.07
     प्रथम
    0.07
    asis
    0.07
    Activations Density 0.002%

    No Known Activations