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. 42225
    Prev
    Next
    INDEX
    Explanations

    and

    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
     भनेर
    -0.08
     altså
    -0.08
     erhe
    -0.08
    _POLICY
    -0.08
    Assign
    -0.07
     alltså
    -0.07
    inon
    -0.07
     ব্য
    -0.07
    _assign
    -0.07
     connus
    -0.07
    POSITIVE LOGITS
     ngang
    0.08
    #m
    0.08
     commas
    0.08
     �
    0.07
    ИЙ
    0.07
     Bang
    0.07
    wia
    0.07
     Economy
    0.07
     �
    0.07
     Cro
    0.07
    Activations Density 0.001%

    No Known Activations