© 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. 11-RESID-POST-AA
    11. 31585
    Prev
    Next
    INDEX
    Explanations

    mathematical/computational problem-solving

    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
    -pr
    -0.07
     Can
    -0.07
    Jak
    -0.07
     Hav
    -0.07
     можете
    -0.07
     Jak
    -0.07
    _pr
    -0.07
    .pr
    -0.07
    Goal
    -0.07
     дос
    -0.07
    POSITIVE LOGITS
     bt
    0.09
    (bt
    0.09
    	bt
    0.09
     odnosno
    0.08
     alright
    0.08
     elenco
    0.08
    úde
    0.08
    itoris
    0.08
     ставок
    0.07
    િતિ
    0.07
    Activations Density 0.275%

    No Known Activations