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. 54127
    Prev
    Next
    INDEX
    Explanations

    Moving toward each other

    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
    铭
    -0.08
     túl
    -0.08
    ži
    -0.07
     Kors
    -0.07
     béton
    -0.07
    ுப
    -0.07
     gloss
    -0.07
    robat
    -0.07
     Mig
    -0.07
    ashin
    -0.07
    POSITIVE LOGITS
     carriage
    0.09
     двер
    0.08
     steadily
    0.08
     نحو
    0.08
     menuju
    0.08
     strangers
    0.08
     arah
    0.08
     taxis
    0.07
     yönelik
    0.07
     towards
    0.07
    Activations Density 0.005%

    No Known Activations