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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 30972
    Prev
    Next
    INDEX
    Explanations

    speech pathology and dietetics

    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
    ＿
    -0.09
     manche
    -0.08
    	rep
    -0.07
    いただ
    -0.07
     trên
    -0.07
     ciphertext
    -0.07
    .bid
    -0.07
     מער
    -0.07
    Quoted
    -0.07
     Returning
    -0.07
    POSITIVE LOGITS
    pleeg
    0.09
     discapacidad
    0.08
     therapist
    0.08
    vermittlung
    0.08
    师
    0.08
     дисп
    0.08
     intervent
    0.08
     diet
    0.08
    catch
    0.07
     kiko
    0.07
    Activations Density 0.017%

    No Known Activations