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. 97126
    Prev
    Next
    INDEX
    Explanations

    اقت

    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
    ido
    -0.08
    orro
    -0.07
    hes
    -0.07
    aku
    -0.07
    ajes
    -0.07
    帯
    -0.07
    atischen
    -0.07
     ಕ್ರ
    -0.07
    -gu
    -0.07
     do
    -0.07
    POSITIVE LOGITS
    راح
    0.10
    ريح
    0.09
     straighten
    0.08
     relativement
    0.08
     waarde
    0.08
     ****
    0.08
    °
    0.08
    488
    0.08
    ిస్తున్న
    0.08
    udge
    0.07
    Activations Density 0.000%

    No Known Activations