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. 130986
    Prev
    Next
    INDEX
    Explanations

    измен

    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
    ത്തില്
    -0.09
    	column
    -0.08
    熱門
    -0.08
    colour
    -0.08
    热门
    -0.08
     സംഘം
    -0.08
     unin
    -0.07
     সময়
    -0.07
     populaire
    -0.07
     posterior
    -0.07
    POSITIVE LOGITS
    ylinder
    0.08
     qq
    0.08
    qq
    0.08
     стороны
    0.08
    илось
    0.08
     Adds
    0.08
    _here
    0.08
    /comment
    0.07
    ■
    0.07
     Hemisphere
    0.07
    Activations Density 0.001%

    No Known Activations