© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 97839
    Prev
    Next
    INDEX
    Explanations

    calculus problems

    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
     kanthi
    -0.09
     Across
    -0.09
     poursuivre
    -0.09
     учетом
    -0.08
     гэтай
    -0.08
     wannan
    -0.08
     anhand
    -0.08
     postpon
    -0.08
     targ
    -0.08
     гэтага
    -0.08
    POSITIVE LOGITS
     precisely
    0.11
     بعض
    0.10
     exactly
    0.10
    /in
    0.10
     initially
    0.10
     لبعض
    0.10
    /not
    0.10
     برخی
    0.10
    -negative
    0.10
     except
    0.09
    Activations Density 0.047%

    No Known Activations