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. 98226
    Prev
    Next
    INDEX
    Explanations

    ISO certifications

    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
     টি
    -0.08
     posso
    -0.08
     possibilities
    -0.08
     pleas
    -0.08
     دانشگاه
    -0.08
     universidade
    -0.08
     جامعة
    -0.07
     pensa
    -0.07
    _assign
    -0.07
     largement
    -0.07
    POSITIVE LOGITS
     troublesome
    0.08
    nv
    0.08
    andid
    0.08
     Listing
    0.07
    				       
    0.07
    ła
    0.07
    Go
    0.07
     Svenska
    0.07
     brasile
    0.07
    ैंड
    0.07
    Activations Density 0.000%

    No Known Activations