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. 97960
    Prev
    Next
    INDEX
    Explanations

    Aerodynamics/Aerobics

    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
     trusting
    -0.08
    ragt
    -0.08
     Trust
    -0.07
    stvu
    -0.07
     trusts
    -0.07
    reit
    -0.07
     accepter
    -0.07
     discrepancies
    -0.07
     unap
    -0.07
     courtroom
    -0.07
    POSITIVE LOGITS
    obic
    0.13
    odynamic
    0.12
    ated
    0.12
    opuerto
    0.12
    ogel
    0.12
    ation
    0.11
    ating
    0.10
    odynamics
    0.10
    obie
    0.09
    ugin
    0.09
    Activations Density 0.001%

    No Known Activations