Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12675
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities and expressions

    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
     त
    -0.09
     poke
    -0.08
     देना
    -0.08
     यांनी
    -0.08
     hak
    -0.08
     Frankfurt
    -0.08
     फ्र
    -0.08
     मास
    -0.07
     संभ
    -0.07
    ystone
    -0.07
    POSITIVE LOGITS
     everytime
    0.10
     inherently
    0.09
     항상
    0.09
     always
    0.09
    Always
    0.09
     everywhere
    0.09
     دائما
    0.09
     ہمیشہ
    0.09
     altijd
    0.09
     Always
    0.08
    Activations Density 0.030%

    No Known Activations