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. 130956
    Prev
    Next
    INDEX
    Explanations

    Kr/кр

    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
    ahit
    -0.09
    ovit
    -0.08
     hopen
    -0.08
    ov
    -0.08
    hail
    -0.08
     hypoc
    -0.08
    hatian
    -0.08
    versa
    -0.08
    ខ
    -0.08
    avance
    -0.08
    POSITIVE LOGITS
    ishna
    0.11
    ांति
    0.09
    aken
    0.08
    ещение
    0.08
    ీస
    0.08
    ubmit
    0.08
    ిస్ట
    0.08
    ест
    0.08
    ిల్ల
    0.08
    ille
    0.07
    Activations Density 0.003%

    No Known Activations