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. 113040
    Prev
    Next
    INDEX
    Explanations

    pulse width modulation

    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
    ssss
    -0.07
    stags
    -0.07
     examin
    -0.07
     staged
    -0.07
    .lex
    -0.07
     elevados
    -0.07
     overlooked
    -0.07
     microsc
    -0.07
    	struct
    -0.07
     estrutur
    -0.07
    POSITIVE LOGITS
     servo
    0.13
    راوح
    0.12
     PWM
    0.11
     Servo
    0.10
    _RANGE
    0.10
     centimeter
    0.10
    Servo
    0.10
     диапаз
    0.10
     joystick
    0.10
    PWM
    0.09
    Activations Density 0.004%

    No Known Activations