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. 106150
    Prev
    Next
    INDEX
    Explanations

    dental implants

    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
    Observ
    -0.08
     шест
    -0.08
     HEX
    -0.08
     zus
    -0.08
    HEX
    -0.08
    Kod
    -0.08
    .hex
    -0.08
     hexadecimal
    -0.08
    Hex
    -0.07
    hex
    -0.07
    POSITIVE LOGITS
     solución
    0.08
     liger
    0.08
     восстанов
    0.08
     soluzione
    0.08
     लगाए
    0.08
     Replacement
    0.08
     restored
    0.08
     replaces
    0.08
    älle
    0.07
     clás
    0.07
    Activations Density 0.010%

    No Known Activations