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. 112995
    Prev
    Next
    INDEX
    Explanations

    Red Sea

    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
     tides
    -0.09
    غيير
    -0.08
     tidal
    -0.08
    -0.08
     App
    -0.07
     Sir
    -0.07
     Toronto
    -0.07
     Shadow
    -0.07
     Meteor
    -0.06
     tide
    -0.06
    POSITIVE LOGITS
     stim
    0.09
     cubierta
    0.09
     loopt
    0.09
    攻略
    0.09
    strate
    0.08
    Listado
    0.08
    tabla
    0.08
    laş
    0.08
     πλη
    0.08
     मंदिर
    0.08
    Activations Density 0.004%

    No Known Activations