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. 88195
    Prev
    Next
    INDEX
    Explanations

    Vague, broad topics

    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
    AS
    -0.09
     AS
    -0.09
    asi
    -0.08
    ASIL
    -0.08
    ASI
    -0.08
    uryo
    -0.08
    asib
    -0.08
    -AS
    -0.08
     jaw
    -0.08
     �
    -0.07
    POSITIVE LOGITS
     Tools
    0.09
     Lost
    0.08
     throwable
    0.08
     Thoughts
    0.08
    interrupt
    0.08
     diffuser
    0.08
     рабочего
    0.08
    çinin
    0.08
    goods
    0.08
     footprint
    0.08
    Activations Density 0.000%

    No Known Activations