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. 19438
    Prev
    Next
    INDEX
    Explanations

    radius or length

    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
    Storm
    -0.08
    ская
    -0.07
     perfekte
    -0.07
    queeze
    -0.07
     integral
    -0.07
     embodiment
    -0.07
    anni
    -0.07
    ippe
    -0.07
    Für
    -0.07
    Green
    -0.07
    POSITIVE LOGITS
    ٍ
    0.11
     tertentu
    0.10
     معينة
    0.09
     zéro
    0.09
     ○
    0.08
     yacc
    0.08
    =x
    0.08
     �
    0.08
     �
    0.08
     cero
    0.08
    Activations Density 0.027%

    No Known Activations