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. 98613
    Prev
    Next
    INDEX
    Explanations

    �

    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
    ğraf
    -0.09
    hañ
    -0.08
     Projectile
    -0.08
     அரச
    -0.08
     kompl
    -0.08
    -polit
    -0.08
     unpopular
    -0.08
    ’ya
    -0.07
     participado
    -0.07
     relativ
    -0.07
    POSITIVE LOGITS
    �
    0.10
     ng
    0.08
    �
    0.08
     két
    0.08
    �物
    0.08
    泡
    0.08
    ోట
    0.07
    ocyte
    0.07
    ింప
    0.07
    �
    0.07
    Activations Density 0.001%

    No Known Activations