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. 117513
    Prev
    Next
    INDEX
    Explanations

    physics

    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
     with
    -0.07
    261
    -0.07
     engagement
    -0.07
     nive
    -0.07
    270
    -0.07
     and
    -0.07
    163
    -0.07
    160
    -0.07
    esto
    -0.07
     rates
    -0.07
    POSITIVE LOGITS
     ухуд
    0.10
    	ON
    0.09
    분
    0.09
     Ён
    0.09
     Най
    0.09
    튜
    0.08
    .dex
    0.08
    �
    0.08
    ыло
    0.08
     эв
    0.08
    Activations Density 0.001%

    No Known Activations