Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 30845
    Prev
    Next
    INDEX
    Explanations

    In

    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
            ↵
    -0.07
    ustry
    -0.07
    נו
    -0.07
    lua
    -0.07
     tr
    -0.07
     कृ
    -0.07
    Constraints
    -0.07
     clasp
    -0.07
     retorno
    -0.07
                     ↵
    -0.07
    POSITIVE LOGITS
     Santos
    0.09
     Jeffrey
    0.08
     ود
    0.08
     Josh
    0.08
     Haley
    0.08
     ين
    0.08
     Jorn
    0.08
     THESE
    0.08
     Jelly
    0.07
     COL
    0.07
    Activations Density 0.324%

    No Known Activations