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. 98019
    Prev
    Next
    INDEX
    Explanations

    nucleic acids

    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
    ihi
    -0.08
    175
    -0.08
    istors
    -0.08
    ம்ம
    -0.08
    nung
    -0.08
    Enough
    -0.08
    riy
    -0.08
    네요
    -0.07
     Vy
    -0.07
     Ruby
    -0.07
    POSITIVE LOGITS
    ot
    0.17
     acids
    0.15
    酸
    0.14
     acid
    0.13
     Acid
    0.13
    acid
    0.12
    otide
    0.11
    ophile
    0.11
    OT
    0.10
     acidic
    0.10
    Activations Density 0.001%

    No Known Activations