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. 11-RESID-POST-AA
    6. 106324
    Prev
    Next
    INDEX
    Explanations

    charitable

    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
    如今
    -0.09
     stoel
    -0.08
     twins
    -0.08
     Antonio
    -0.08
     nurse
    -0.07
    олд
    -0.07
     paciente
    -0.07
     FRONT
    -0.07
     sóc
    -0.07
     nurses
    -0.07
    POSITIVE LOGITS
    _org
    0.08
    nete
    0.08
    amiseen
    0.08
     компаний
    0.07
    _example
    0.07
    issent
    0.07
    _ch
    0.07
    _OR
    0.07
     inté
    0.07
    'esp
    0.07
    Activations Density 0.010%

    No Known Activations