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. 98051
    Prev
    Next
    INDEX
    Explanations

    foreign question words

    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
     whether
    -0.09
    whether
    -0.09
    ولاية
    -0.09
     what's
    -0.08
    Количество
    -0.08
    Ҡ
    -0.08
     thata
    -0.08
     whose
    -0.08
     पुगे
    -0.08
    	std
    -0.08
    POSITIVE LOGITS
     എ
    0.24
     எ
    0.22
     როგორ
    0.19
     чӣ
    0.18
     ఎ
    0.18
     რატომ
    0.18
    ఎ
    0.18
    എ
    0.17
     ինչպես
    0.17
    როგ
    0.15
    Activations Density 0.012%

    No Known Activations