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. 130942
    Prev
    Next
    INDEX
    Explanations

    tach

    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
     mahu
    -0.07
     Cham
    -0.07
     गये
    -0.07
    ђе
    -0.07
    ಒ
    -0.07
     levant
    -0.07
     moss
    -0.07
    -0.07
     extinct
    -0.07
     elevado
    -0.07
    POSITIVE LOGITS
    hythm
    0.14
    ygy
    0.13
    yon
    0.13
    yp
    0.13
    y
    0.12
    ys
    0.11
    ogram
    0.11
    card
    0.10
     cardiac
    0.10
    yth
    0.10
    Activations Density 0.002%

    No Known Activations