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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98377
    Prev
    Next
    INDEX
    Explanations

    film references

    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
    oyle
    -0.08
    uhin
    -0.07
    ূল
    -0.07
    後
    -0.07
    ahara
    -0.07
     pohod
    -0.07
     Foot
    -0.07
    ulada
    -0.07
    ที
    -0.07
     آخ
    -0.07
    POSITIVE LOGITS
    )find
    0.08
    ിയുടെ
    0.08
    ersonal
    0.08
    halter
    0.08
    FF
    0.07
     arbete
    0.07
     estable
    0.07
     deline
    0.07
    αν
    0.07
     അ
    0.07
    Activations Density 0.001%

    No Known Activations