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. 45739
    Prev
    Next
    INDEX
    Explanations

    Russian related to interpolation

    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
     fryer
    -0.08
     bull
    -0.08
     loves
    -0.08
     बज
    -0.07
     Infant
    -0.07
     বাজ
    -0.07
     dirig
    -0.07
    oauth
    -0.07
     perpetrators
    -0.07
     Bull
    -0.07
    POSITIVE LOGITS
     interpol
    0.09
     extrap
    0.09
     interpolation
    0.09
     interp
    0.09
    .interpolate
    0.09
     triang
    0.09
    Interpol
    0.09
     interpolate
    0.09
    Bezier
    0.08
    Aus
    0.08
    Activations Density 0.004%

    No Known Activations