© 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. 23-RESID-POST-AA
    11. 6296
    Prev
    Next
    INDEX
    Explanations

    �

    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
     beheer
    -0.08
    inare
    -0.08
     BG
    -0.08
    529
    -0.08
     yp
    -0.08
    (existing
    -0.07
     व्यव
    -0.07
     abak
    -0.07
     Fil
    -0.07
    903
    -0.07
    POSITIVE LOGITS
    Ultra
    0.09
    ray
    0.09
    quad
    0.08
    quanto
    0.08
    joint
    0.08
     ultra
    0.08
     jointly
    0.08
    াল
    0.07
    join
    0.07
    toa
    0.07
    Activations Density 0.001%

    No Known Activations