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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98194
    Prev
    Next
    INDEX
    Explanations

    dors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSLocalized
    -0.08
     ಆಸ
    -0.08
    νας
    -0.08
    eregister
    -0.07
     ўва
    -0.07
    DEVICE
    -0.07
     ಸೋ
    -0.07
    ASHION
    -0.07
    એસ
    -0.07
    PROP
    -0.07
    POSITIVE LOGITS
    end
    0.11
    endt
    0.10
     end
    0.09
    _copy
    0.09
    .copy
    0.09
    .end
    0.09
    copy
    0.09
    _end
    0.08
    pill
    0.08
     copy
    0.08
    Activations Density 0.001%

    No Known Activations