© 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. 108681
    Prev
    Next
    INDEX
    Explanations

    Media references

    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
    ovar
    -0.08
    .em
    -0.07
     Faculdade
    -0.07
    inking
    -0.07
    வும்
    -0.07
    irical
    -0.07
     Fingers
    -0.07
     gült
    -0.07
    வு
    -0.07
     staggering
    -0.07
    POSITIVE LOGITS
    83
    0.10
    26
    0.09
    9
    0.09
    692
    0.09
    06
    0.09
     hau
    0.09
    21
    0.09
    86
    0.09
    82
    0.09
    38
    0.09
    Activations Density 0.029%

    No Known Activations