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. 53093
    Prev
    Next
    INDEX
    Explanations

    translation

    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
    -buffer
    -0.09
    -road
    -0.08
    _detect
    -0.08
    -profile
    -0.08
    _dirty
    -0.08
    _eye
    -0.08
    _invalid
    -0.08
    _alpha
    -0.08
     wachsen
    -0.07
    Growing
    -0.07
    POSITIVE LOGITS
     translations
    0.12
     counterparts
    0.11
     перевод
    0.10
    訳
    0.10
     mappings
    0.10
    translations
    0.10
     traduction
    0.09
     translation
    0.09
     বিদেশ
    0.09
     अंग्रेज
    0.09
    Activations Density 0.016%

    No Known Activations