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. 7-RESID-POST-AA
    6. 131061
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Numer
    -0.08
    -skilled
    -0.08
     lad
    -0.08
    Christine
    -0.07
    andi
    -0.07
    Numer
    -0.07
     अभिय
    -0.07
    ierig
    -0.07
    ians
    -0.07
     clinicians
    -0.07
    POSITIVE LOGITS
     �
    0.09
    wm
    0.08
    bum
    0.08
     mener
    0.07
    ρα
    0.07
     avancer
    0.07
    جھ
    0.07
     mé
    0.07
     spaces
    0.07
     vouloir
    0.07
    Activations Density 0.005%

    No Known Activations