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. 61056
    Prev
    Next
    INDEX
    Explanations

    す

    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
    movies
    -0.08
     做
    -0.08
    рак
    -0.07
    صفات
    -0.07
     orgull
    -0.07
     tren
    -0.07
    UNCH
    -0.07
     {|
    -0.07
     Cottage
    -0.07
     movies
    -0.07
    POSITIVE LOGITS
     данным
    0.10
     transl
    0.09
     wrench
    0.08
     you're
    0.08
    iya
    0.08
     AE
    0.08
     wireless
    0.08
    pires
    0.08
     Eph
    0.07
    Xp
    0.07
    Activations Density 0.000%

    No Known Activations