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. 9195
    Prev
    Next
    INDEX
    Explanations

    noble truths

    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
    启
    -0.08
     schon
    -0.08
    ül
    -0.08
     truc
    -0.08
    قي
    -0.08
     amazing
    -0.08
     logr
    -0.07
     blends
    -0.07
     abode
    -0.07
     إنها
    -0.07
    POSITIVE LOGITS
    Tours
    0.07
    ference
    0.07
    ortal
    0.07
    Seattle
    0.07
     baut
    0.07
    (tag
    0.07
     decompress
    0.07
     ndaj
    0.07
    aters
    0.07
    BD
    0.07
    Activations Density 0.000%

    No Known Activations