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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-RESID-POST-AA
    6. 19131
    Prev
    Next
    INDEX
    Explanations

    mathematical forumlae

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lecture
    -0.08
     नम्बर
    -0.08
     Pitch
    -0.08
     კიდევ
    -0.08
     شمېر
    -0.08
     sjál
    -0.07
     сөйл
    -0.07
     bahawa
    -0.07
     कुरा
    -0.07
     ორი
    -0.07
    POSITIVE LOGITS
    dbname
    0.07
     puissance
    0.07
    494
    0.07
    coef
    0.07
     barns
    0.07
    tri
    0.07
    fname
    0.07
     unrival
    0.07
     designation
    0.07
    mega
    0.07
    Activations Density 0.040%

    No Known Activations