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. 19175
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
     python
    -0.08
     noting
    -0.08
    ектив
    -0.08
     Python
    -0.08
    。,
    -0.07
    成为
    -0.07
    作为
    -0.07
    此前
    -0.07
     Flip
    -0.07
     Variante
    -0.07
    POSITIVE LOGITS
     அல்லது
    0.11
     hoặc
    0.10
     disa
    0.09
     또는
    0.09
     diferents
    0.09
     կամ
    0.09
    /st
    0.09
    /g
    0.09
    หรือ
    0.09
     yoki
    0.09
    Activations Density 0.005%

    No Known Activations