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. 98284
    Prev
    Next
    INDEX
    Explanations

    Non-english text

    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
    үд
    -0.11
    ન્દ્ર
    -0.11
    જરાત
    -0.10
    ғини
    -0.10
    િંદ
    -0.10
    geber
    -0.10
    ર્સ
    -0.10
    íodh
    -0.10
    ғур
    -0.10
     Sparks
    -0.10
    POSITIVE LOGITS
    čku
    0.12
    nu
    0.10
    jej
    0.10
    losti
    0.09
    ku
    0.09
    ti
    0.09
    ci
    0.09
     ti
    0.09
     si
    0.09
    ej
    0.09
    Activations Density 0.003%

    No Known Activations