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. 11-RESID-POST-AA
    6. 60993
    Prev
    Next
    INDEX
    Explanations

    ose

    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
     клав
    -0.08
    �
    -0.08
     thrills
    -0.08
    梦想
    -0.08
     ambition
    -0.08
    _keyboard
    -0.08
     jäl
    -0.08
     Kimber
    -0.08
     dromen
    -0.08
     birt
    -0.08
    POSITIVE LOGITS
    \Fac
    0.08
    {sub
    0.08
     pard
    0.08
     fallo
    0.07
    ισε
    0.07
     Israelites
    0.07
     Fakult
    0.07
    xbb
    0.07
     Kapoor
    0.07
     UAE
    0.07
    Activations Density 0.001%

    No Known Activations