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. 76437
    Prev
    Next
    INDEX
    Explanations

    Code

    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
     accession
    -0.09
    _IR
    -0.09
    .thrift
    -0.09
     quorum
    -0.09
     Telerik
    -0.09
     Verizon
    -0.09
     Webinar
    -0.09
     transcripts
    -0.08
     Perl
    -0.08
     Genes
    -0.08
    POSITIVE LOGITS
    pygame
    0.16
     pygame
    0.14
    	SDL
    0.13
    Joystick
    0.12
     joystick
    0.11
     اللعبة
    0.11
    /font
    0.11
     sprite
    0.11
    .sprite
    0.11
    .blit
    0.11
    Activations Density 0.016%

    No Known Activations