Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 111631
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RS
    -0.09
    ایی
    -0.08
    ETS
    -0.08
    DK
    -0.08
    “大
    -0.08
     lob
    -0.08
    Tal
    -0.08
     RB
    -0.07
     BK
    -0.07
    _EXTERN
    -0.07
    POSITIVE LOGITS
    sortable
    0.08
    Scrollable
    0.08
     ecstatic
    0.08
     scrolling
    0.08
     runnable
    0.08
    -a
    0.07
     soul
    0.07
     Observable
    0.07
    Clickable
    0.07
     crying
    0.07
    Activations Density 0.004%

    No Known Activations