Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 78625
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
    Aligned
    -0.08
    _CM
    -0.08
    定
    -0.08
    _C
    -0.07
     comprado
    -0.07
    teko
    -0.07
     Trap
    -0.07
     تعیین
    -0.07
     находится
    -0.07
     )↵
    -0.07
    POSITIVE LOGITS
    _epochs
    0.09
     journées
    0.09
     exhibitions
    0.08
    Verts
    0.08
     Muhammad
    0.08
     outings
    0.08
     masturbation
    0.08
     taxis
    0.08
     vowels
    0.08
    老人
    0.08
    Activations Density 0.067%

    No Known Activations