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. 88131
    Prev
    Next
    INDEX
    Explanations

    logic

    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
    -earth
    -0.08
     earth
    -0.08
     thousands
    -0.08
     Series
    -0.08
     �
    -0.07
     electric
    -0.07
     Electric
    -0.07
     embossed
    -0.07
     brush
    -0.07
     Earth's
    -0.07
    POSITIVE LOGITS
     conjunct
    0.10
     Bool
    0.10
     propos
    0.10
     epistem
    0.09
    .bool
    0.09
     liar
    0.09
     conjunction
    0.09
    False
    0.09
    Condition
    0.09
     AND
    0.09
    Activations Density 0.017%

    No Known Activations